Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Dannykkh/skill-olympus --skill zepherminegit clone --depth 1 https://github.com/Dannykkh/skill-olympusWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/dannykkh/skill-olympus/zephermine)<a href="https://agentmods.dev/skills/dannykkh/skill-olympus/zephermine"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/zephermine/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dannykkh/skill-olympus/zephermine"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/zephermine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 639 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 641 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00097 | $0.10235 |
| Opus 5 | $0.00048 | $0.05117 |
| Sonnet 5 | $0.00019 | $0.02047 |
| Haiku 4.5 | $0.00010 | $0.01023 |
Grade A, and why
zephermine scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 684 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zephermine
Zephyr(제퍼: 산들바람/서풍, 부드럽고 빠른 흐름) + Minerva(미네르바: 지혜·전략·판단)의 합성어. 바람처럼 가볍고 빠르게 상황을 읽고, 미네르바처럼 논리적으로 설계해 실행 가능한 계획으로 만드는 능력을 뜻합니다. softaworks/gepetto 스킬을 벤치마킹하여 커스터마이징한 버전입니다.
Orchestrates a multi-step planning process: Research → Interview → Spec Synthesis → Team Analysis → Plan → External Review → Sections → Verify
네이티브 plan mode와의 구분: 현재 CLI가 제공하는 plan mode는 "이 작업을 어떻게 구현할까"를 다루는 단일 작업용 계획 승인 게이트이고, 젭마인은 다운스트림(포세이돈·아르고스·미노스·제우스·견적)이 소비하는 디스크 아티팩트(plan.md, sections/, flow-diagrams/, qa-scenarios)를 만드는 설계 파이프라인입니다. 단일 버그픽스·소규모 리팩토링은 plan mode, 기능/제품 단위 설계는 젭마인. Antigravity에서는 가벼운 구현 계획은
/plan, 누락 요구를 집중 인터뷰로 좁히는 일은/grill-me가 먼저입니다. 그 결과만 필요하면 젭마인을 시작하지 않습니다.spec.md, 도메인 사전, API/DB, flow, sections, operation/QA 시나리오까지 디스크에 남겨 downstream이 소비해야 할 때만 젭마인을 사용합니다. slash command를 프로그램적으로 호출한다고 가정하지 않으며, 현재 plan mode가 쓰기·승인 전용이면 그 안에서 젭마인을 실행하지 않습니다. 사용자가 만든 네이티브 계획·인터뷰 결과는 쓰기 가능한 모드에서 입력으로 이어받습니다.
CRITICAL: First Actions
BEFORE anything else, do these in order:
1. Print Intro
간결하게 진행 순서만 출력:
젭마인(Zephermine) 시작
순서: Research → Blindspot → Interview → Spec(+Domain Dictionary v1) → Persona/Journey → Team Review(+Dictionary v3) → Plan → External Review → DB Schema → API Spec → Flow Diagrams → Sections → Operation Scenarios → QA Scenarios → Skill Discovery
2. Resolve Spec File Path
Check if user provided @file at invocation AND it's a spec file (ends with .md).
경로가 제공된 경우: 그대로 사용
경로가 없는 경우: 사용자 대화에서 주제를 추론하여 자동 경로 생성 후 바로 진행:
- 대화 컨텍스트에서 기능/프로젝트명 추출 (예: "UI 재설계" →
ui-redesign) - 기본 경로 패턴:
docs/plan/{feature-name}/spec.md - 사용자에게 경로만 간단히 확인:
계획 경로: docs/plan/ui-redesign/spec.md 이 경로로 진행합니다. (변경하려면 알려주세요) - 확인을 기다리지 않고 바로 다음 단계 진행 (사용자가 변경 요청하면 그때 수정)
주제를 추론할 수 없는 경우에만 간단히 질문:
어떤 기능을 계획할까요? (예: "로그인 리팩토링", "결제 시스템")
3. Setup Planning Session
Determine session state by checking existing files:
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 295 B
- references/api-spec-guide.md 4.5 KB
- references/design-system-guide.md 6.5 KB
- references/domain-confirmation-guide.md 3.6 KB
- references/external-review.md 6.5 KB
- references/flow-diagrams-guide.md 3.7 KB
- references/interview-protocol.md 17 KB
- references/operation-qa-guide.md 2.3 KB
- references/persona-journey-guide.md 1.7 KB
- references/research-protocol.md 21 KB
- references/schema-design-guide.md 7.0 KB
- references/section-index.md 6.0 KB
- references/section-splitting.md 7.8 KB
- references/team-review-protocol.md 40 KB
- references/test-scenario-guide.md 4.9 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 684 lines · 97 tokens per session scan A c8831253edc9
zephermine is a skill published in the GitHub repository Dannykkh/skill-olympus (5 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 10,235 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.
Other skills, from other repositories
factory-close
Close out a Linear issue — move to Done, add a closing comment, and clean up the local branch/worktree.
factory-setup-linear
Configure portable Linear workflow settings in .factory-kit/linear.json, migrating legacy .claude/linear.json settings when present.
factory-submit
Move the current branch's Linear issue to "In Review".
factory-entry
Load a Linear issue into context and enter plan mode for a focused session.
factory-standup
Dev standup — open Linear tickets grouped by in-flight, top priority, and backlog.
implement-batch
Use when you want to implement the next batch of a plan. Handles module implementation, testing, and validation.